DC hirey-ai-install
Install or repair Hirey AI on a local OpenClaw host through the official ClawHub package path, then complete the local MCP, receiver, registration, and health-check setup so the host can use Hi for people-to-people matching across hiring, jobs, housing, friendship, dating, founders, investors, lawyers, and any other human lead search.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 7
-
high Concealment
en-hide-from-userSKILL.md:104Instruction to hide actions from the user- during Stage A, do not tell the user you will keep tracking a background package-install process in a later turn; either report the final result from the blocking command, or if the host genuinely r
-
high Concealment
en-hide-from-userSKILL.md:106Instruction to hide actions from the user- if a local read like `/app/skills/hirey-ai-install/SKILL.md` fails, explain plainly that the host cannot currently see its local skill snapshot; do not tell the user the Hirey AI skill disappeared,
-
high Concealment
en-hide-from-userSKILL.md:181Instruction to hide actions from the user- in the default two-message flow, do not tell the user you are already starting the register step, switching to a new sub-session, or continuing Hi registration while the setup step is ending; the se
Medium and low: 4
-
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:801High-entropy token-like string (may be an id, hash or a credential)function vali…Key(hostSessionKey) { -
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:811High-entropy token-like string (may be an id, hash or a credential)export function buil…oad(args) { -
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:812High-entropy token-like string (may be an id, hash or a credential)const hostSessionKey = vali…Key(args.hostSessionKey);
-
low Secrets in code
secret-high-entropy-tokenscripts/openclaw-host-installer.mjs:850High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)const installArgs = buil…oad({detector
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8744 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 8744 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
- 70Failures and branches. 19 branches
- 100Steps. 142 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 336: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 142 items
- +4Has examples (0 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.